A Hybrid ANFIS-GA Approach for Estimation of Hydrological Time Series

Haznedar, Bülent; Kilinç, Hüseyin Çağan

doi:10.1007/s11269-022-03280-4

Cited by 12 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the operational control requirements of power stations differ substantially from the changing characteristics of the grid load, direct determination of reasonable segmentation points on the load curve poses considerable challenges. The objective of denoising the load time series is to develop an algorithm that disregards minor fluctuations and identifies significant peaks and troughs that define the time series' general shape [23]. The HPLA [24], proposed by Vineetha Bettaiah in 2014, ignores minor fluctuations and discerns the overall trend and significant peaks and valleys of the loaded time series.…”

Section: Time Series Smoothing Conceptmentioning

confidence: 99%

See 1 more Smart Citation

An Advanced Peaking Method for Improved Hydropower Plant Regulation and Power Grid Management

Chang

Zhang

2023

Preprint

View full text Add to dashboard Cite

Hydropower, as a crucial component of power grid systems, plays an essential role in peak regulation due to its fast start-stop and high-speed climbing capabilities. Current hydropower peak regulation methods struggle to consider complex load demand and the highly coupled characteristics of runoff simultaneously. This study proposes the Adaptive Segmented Cutting Load Algorithm (ASCLA) to restructure the power station's load process and segment the scheduling period based on load characteristics, ensuring hydropower stations operate in peak regulation mode throughout the entire cycle. The method determines each sub-scheduling period's peak regulation depth based on runoff characteristics and considers factors impacting peak regulation capability. To minimize the residual load's rolling data window standard deviation, we apply ASCLA to the Three Gorges Reservoir (TGR) simulation. We introduce four evaluation indicators: Mean Squared Deviation of the Rolling Window (MSDRW), total time variation of residual load, peak residual load, and response time to assess peak regulation effectiveness. Our method can handle peak regulation demands under varying runoff conditions, providing feasible scheduling solutions. Simulations and analyses reveal ASCLA demonstrates stronger load tracking ability, a broader adjustment range of load peaks and valleys, and a more significant peak regulation effect compared to the conventional method. Finer segmentation of sub-scheduling periods and final water level determination under conditions of higher load variability and drier runoff optimizes the power station's regulation capacity and meets the power grid's operational needs. In conclusion, our research develops a comprehensive and adaptable peak regulation scheduling model for hydropower stations, offering more effective solutions to address challenges related to extreme weather events and renewable energy integration.

show abstract

Section: Time Series Smoothing Conceptmentioning

confidence: 99%

“…for the station in sub-dispatch period m as shown in Eq(23): If met, then the water consumption during the dispatch period is too high, and the reservoir cannot be stored to the required level. In this case, update position position =+…”

mentioning

confidence: 99%

An Advanced Peaking Method for Improved Hydropower Plant Regulation and Power Grid Management

Chang

Zhang

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In the same perspective, Haznedar and Kilinc 29 developed a hybrid ANFIS model with an integrated genetic algorithm (GA) (ANFIS-GA) for streamflow prediction, using its past values as input. The outcomes demonstrated that the suggested model performs better than the standard ANFIS, LSTM, and ANN.…”

Section: Introductionmentioning

confidence: 99%

Short-term streamflow modeling using data-intelligence evolutionary machine learning models

Martinho,

Hippert,

Goliatt

2023

Sci Rep

View full text Add to dashboard Cite

Accurate streamflow prediction is essential for efficient water resources management. Machine learning (ML) models are the tools to meet this need. This paper presents a comparative research study focusing on hybridizing ML models with bioinspired optimization algorithms (BOA) for short-term multistep streamflow forecasting. Specifically, we focus on applying XGB, MARS, ELM, EN, and SVR models and various BOA, including PSO, GA, and DE, for selecting model parameters. The performances of the resulting hybrid models are compared using performance statistics, graphical analysis, and hypothesis testing. The results show that the hybridization of BOA with ML models demonstrates significant potential as a data-driven approach for short-term multistep streamflow forecasting. The PSO algorithm proved superior to the DE and GA algorithms in determining the optimal hyperparameters of ML models for each step of the considered time horizon. When applied with all BOA, the XGB model outperformed the others (SVR, MARS, ELM, and EN), best predicting the different steps ahead. XGB integrated with PSO emerged as the superior model, according to the considered performance measures and the results of the statistical tests. The proposed XGB hybrid model is a superior alternative to the current daily flow forecast, crucial for water resources planning and management.

show abstract

Monthly River Discharge Forecasting Using Hybrid Models Based on Extreme Gradient Boosting Coupled with Wavelet Theory and Lévy–Jaya Optimization Algorithm

Zhou

Wang

Band

et al. 2023

Water Resour Manage

View full text Add to dashboard Cite

A Hybrid ANFIS-GA Approach for Estimation of Hydrological Time Series

Cited by 12 publications

References 32 publications

An Advanced Peaking Method for Improved Hydropower Plant Regulation and Power Grid Management

An Advanced Peaking Method for Improved Hydropower Plant Regulation and Power Grid Management

Short-term streamflow modeling using data-intelligence evolutionary machine learning models

Monthly River Discharge Forecasting Using Hybrid Models Based on Extreme Gradient Boosting Coupled with Wavelet Theory and Lévy–Jaya Optimization Algorithm

Contact Info

Product

Resources

About